Research

• You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning
  Ayan Sengupta*, Siddhant Chaudhary* and Tanmoy Chakraborty¹
  ICLR 2025, Singapore EXPO
  [pdf] [BibTeX]

• $\alpha$-Fair Contextual Bandits
  Siddhant Chaudhary and Abhishek Sinha
  ICML 2024 workshop on Foundations of RL and Control, Vienna, Austria
  [pdf] [BibTeX] [Code] [Poster]

• Online Subset Selection using $\alpha$-Core with no Augmented Regret
  Sourav Sahoo, Siddhant Chaudhary, Samrat Mukhopadhyay, and Abhishek Sinha
  [Preprint]